torch-named-linops 0.3.10__tar.gz

torch_named_linops-0.3.10/.github/workflows/test-python.yml

@@ -0,0 +1,50 @@
+name: Install, Lint, and Test
+
+on:
+  push:
+    branches:
+      - main
+      - test-actions
+  pull_request: {}
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  python-install-lint-test:
+    name: ${{ matrix.os }} - Python ${{ matrix.python-version }}
+    runs-on: ${{ matrix.os  }}
+    timeout-minutes: 15
+    defaults:
+      run:
+        shell: bash
+    strategy:
+      max-parallel: 5
+      matrix:
+        os: [ubuntu-latest]
+        # deps: ['dev'] # 'test-cuda11' coming soon? https://github.com/github/roadmap/issues/961
+        python-version: ['3.10', '3.11', '3.12']
+      fail-fast: false
+
+    steps:
+    - name: Checkout repo
+      uses: actions/checkout@v4
+    # uv setup
+    - name: Set up python with uv
+      uses: astral-sh/setup-uv@v5
+    - name: Install python
+      run: uv python install ${{ matrix.python-version }}
+    - name: Initialize environment
+      run: uv sync --group all
+    # uv lint and test
+    - name: Lint with ruff
+      run: uv run ruff check
+    - name: Run tests with coverage
+      run: uv run pytest --cov .
+
+    # Generates warnings but still works?
+    - name: Upload coverage reports to Codecov
+      uses: codecov/codecov-action@v5.3.1
+      with:
+        token: ${{ secrets.CODECOV_TOKEN }}

torch_named_linops-0.3.10/.gitignore

@@ -0,0 +1,17 @@
+.DS_Store
+.idea
+*.log
+tmp/
+
+*.py[cod]
+*.egg
+*.egg-info
+build
+dist
+htmlcov
+.coverage
+
+# Data files
+*.np[yz]
+*.mat
+

torch_named_linops-0.3.10/.pre-commit-config.yaml

@@ -0,0 +1,9 @@
+repos:
+- repo: https://github.com/astral-sh/ruff-pre-commit
+  # Ruff version.
+  rev: v0.5.1
+  hooks:
+    # Run the linter.
+    - id: ruff
+    # Run the formatter.
+    - id: ruff-format

torch_named_linops-0.3.10/LICENSE.txt

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2025 Mark Nishimura
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

torch_named_linops-0.3.10/PKG-INFO

@@ -0,0 +1,71 @@
+Metadata-Version: 2.4
+Name: torch-named-linops
+Version: 0.3.10
+Summary: A flexible linear operator abstraction in pytorch.
+Author-email: Mark Nishimura <markn1@stanford.edu>
+License-File: LICENSE.txt
+Requires-Python: >=3.10
+Requires-Dist: einops>=0.8.0
+Requires-Dist: jaxtyping>=0.2.36
+Requires-Dist: setuptools>=75.6.0
+Requires-Dist: torch<2.3,>1.13; sys_platform == 'darwin' and platform_machine == 'x86_64'
+Requires-Dist: torch>=2.5.1; sys_platform != 'darwin' or platform_machine != 'x86_64'
+Requires-Dist: torchaudio<2.3,>1.13; sys_platform == 'darwin' and platform_machine == 'x86_64'
+Requires-Dist: torchaudio>=2.5.1; sys_platform != 'darwin' or platform_machine != 'x86_64'
+Requires-Dist: torchvision<0.20.1; sys_platform == 'darwin' and platform_machine == 'x86_64'
+Requires-Dist: torchvision>=0.20.1; sys_platform != 'darwin' or platform_machine != 'x86_64'
+Requires-Dist: tqdm>=4.67.1
+Requires-Dist: triton>=3.0
+Description-Content-Type: text/markdown
+
+# torch-named-linops
+
+A flexible linear operator abstraction implemented in PyTorch.
+
+Heavily inspired by [einops](https://einops.rocks).
+
+Unrelated to the (also good) [torch_linops](https://github.com/cvxgrp/torch_linops)
+
+## Selected Feature List
+- Dedicated abstraction for naming linear operator dimensions.
+- A set of core linops, including:
+  - `Dense`
+  - `Diagonal`
+  - `FFT`
+  - `ArrayToBlocks`[^*] (similar to PyTorch's [unfold](https://pytorch.org/docs/stable/generated/torch.nn.Unfold.html) but in 1D/2D/3D/arbitrary dimensions)
+    - Useful for local patch extraction
+  - `Interpolate`[^*] (similar to SigPy's
+    [interpolate/gridding](https://sigpy.readthedocs.io/en/latest/generated/sigpy.linop.Interpolate.html))
+     - Comes with `kaiser_bessel` and (1D) `spline` kernels.
+- `.H` and `.N` properties for adjoint $A^H$ and normal $A^HA$ linop creation.
+- `Chain` and `Add` for composing linops together.
+- `Batch` and `DistributedBatch` wrappers for splitting linops temporally on a
+  single GPU, or across multiple GPUs (via `torch.multiprocessing`).
+- Full support for complex numbers. Adjoint takes the conjugate transpose.
+- Full support for `autograd`-based automatic differentiation.
+
+[^*] Includes a `functional` interface and
+[triton](https://github.com/triton-lang/triton) backend for 1D/2D/3D.
+
+## Installation
+### From source (recommended for developers)
+1. Clone the repo with `git clone`
+2. Run `pip install -e .` from the root directory.
+  - Or `uv add path/to/cloned/repo`
+
+3. Pull upstream changes as required.
+
+### Via `pip`'s git integration
+Run the following, replacing `<TAG>` with the appropriate version (e.g. `0.3.7``)
+
+- http version:
+```sh
+$ pip install git+https://github.com/nishi951/torch-named-linops.git@<TAG>
+```
+
+- ssh version:
+``` sh
+$ pip install git+ssh://git@github.com/nishi951/torch-named-linops.git@<TAG>
+```
+
+

torch_named_linops-0.3.10/README.md

@@ -0,0 +1,51 @@
+# torch-named-linops
+
+A flexible linear operator abstraction implemented in PyTorch.
+
+Heavily inspired by [einops](https://einops.rocks).
+
+Unrelated to the (also good) [torch_linops](https://github.com/cvxgrp/torch_linops)
+
+## Selected Feature List
+- Dedicated abstraction for naming linear operator dimensions.
+- A set of core linops, including:
+  - `Dense`
+  - `Diagonal`
+  - `FFT`
+  - `ArrayToBlocks`[^*] (similar to PyTorch's [unfold](https://pytorch.org/docs/stable/generated/torch.nn.Unfold.html) but in 1D/2D/3D/arbitrary dimensions)
+    - Useful for local patch extraction
+  - `Interpolate`[^*] (similar to SigPy's
+    [interpolate/gridding](https://sigpy.readthedocs.io/en/latest/generated/sigpy.linop.Interpolate.html))
+     - Comes with `kaiser_bessel` and (1D) `spline` kernels.
+- `.H` and `.N` properties for adjoint $A^H$ and normal $A^HA$ linop creation.
+- `Chain` and `Add` for composing linops together.
+- `Batch` and `DistributedBatch` wrappers for splitting linops temporally on a
+  single GPU, or across multiple GPUs (via `torch.multiprocessing`).
+- Full support for complex numbers. Adjoint takes the conjugate transpose.
+- Full support for `autograd`-based automatic differentiation.
+
+[^*] Includes a `functional` interface and
+[triton](https://github.com/triton-lang/triton) backend for 1D/2D/3D.
+
+## Installation
+### From source (recommended for developers)
+1. Clone the repo with `git clone`
+2. Run `pip install -e .` from the root directory.
+  - Or `uv add path/to/cloned/repo`
+
+3. Pull upstream changes as required.
+
+### Via `pip`'s git integration
+Run the following, replacing `<TAG>` with the appropriate version (e.g. `0.3.7``)
+
+- http version:
+```sh
+$ pip install git+https://github.com/nishi951/torch-named-linops.git@<TAG>
+```
+
+- ssh version:
+``` sh
+$ pip install git+ssh://git@github.com/nishi951/torch-named-linops.git@<TAG>
+```
+
+

torch_named_linops-0.3.10/dev/cuda_streams/.gitignore

@@ -0,0 +1,12 @@
+.DS_Store
+.idea
+*.log
+tmp/
+
+*.py[cod]
+*.egg
+build
+htmlcov
+
+# Trace files
+*.json

torch_named_linops-0.3.10/dev/cuda_streams/_parallel.py

@@ -0,0 +1,153 @@
+import json
+
+import torch
+import torch.nn as nn
+import torch.multiprocessing as mp
+from torch.profiler import profile, record_function, ProfilerActivity
+
+try:
+    mp.set_start_method("forkserver")
+except RuntimeError:
+    pass
+
+__all__ = ["parallel_call", "merge_traces"]
+
+
+def parallel_call(
+    modules: list[nn.Module],
+    args: list[tuple],
+    do_profile: bool = False,
+):
+    """Run a list of modules on a list of arguments in parallel
+
+    Note: if the modules have any parameters that require gradient, this might not work.
+
+    """
+    if len(modules) != len(args):
+        raise ValueError(
+            f"modules and args must be same length but got {len(modules) } != {len(args)}"
+        )
+    # Initialize input queues, output_queues, and received queues
+    n_procs = len(modules)
+    qins = [mp.Queue() for _ in range(n_procs)]
+    qouts = [mp.Queue() for _ in range(n_procs)]
+    recvs = [mp.Event() for _ in range(n_procs)]
+
+    # Start processes and send data
+    procs = []
+    for rank, mod, args, qin, qout, recv in zip(
+        range(n_procs), modules, args, qins, qouts, recvs
+    ):
+        proc = mp.Process(target=call_module, args=(rank, qin, qout, recv, do_profile))
+        proc.start()
+        qin.put((mod, args))
+        procs.append(proc)
+
+    # Receive data, signal child processes to exit,and join processes
+    outputs = []
+    for proc, qout, recv in zip(procs, qouts, recvs):
+        outputs.append(qout.get())
+        recv.set()
+        proc.join()
+
+    return outputs
+
+
+def call_module(
+    rank: int,
+    qin: mp.Queue,
+    qout: mp.Queue,
+    recv: mp.Event,
+    do_profile: bool = False,
+):
+    """Helper function for parallel call
+
+    rank : int
+        The id of this process
+
+    """
+    # Get module and args from input queue
+    mod, args = qin.get()
+
+    # Run module on args
+    if do_profile:
+        with profile(
+            activities=[ProfilerActivity.CPU, ProfilerActivity.CUDA],
+            on_trace_ready=lambda p: p.export_chrome_trace(
+                f"./worker_{rank}_trace.json"
+            ),
+        ) as prof:
+            out = mod(*args)
+    else:
+        out = mod(*args)
+
+    # Put output in the output queue
+    qout.put(out)
+
+    # Wait for parent process to signal received
+    recv.wait()
+
+
+def merge_traces(input_files, output_file):
+    """
+
+    Example usage
+    trace_files = glob.glob("./worker_*_trace.json")
+    merge_traces(trace_files, "merged_trace.json")
+    """
+    all_traces = {}
+    all_traces["traceEvents"] = []
+
+    for i, trace_file in enumerate(input_files):
+        with open(trace_file, "r") as f:
+            trace_data = json.load(f)
+            events = trace_data["traceEvents"]
+            for event in events:
+                event["pid"] = str(event["pid"]) + f"_{i}"
+
+            # Important step
+            all_traces["traceEvents"].extend(events)
+            # Less important steps
+            all_traces["schemaVersion"] = trace_data["schemaVersion"]
+            all_traces["deviceProperties"] = trace_data["deviceProperties"]
+    all_traces["traceName"] = str(output_file)
+
+    # Write combined traces to a new file
+    with open(output_file, "w") as f:
+        json.dump(all_traces, f)
+
+
+### Testing ###
+class TestAdd(nn.Module):
+    """Needs to be defined at top level of a module"""
+
+    def __init__(self, bias):
+        super().__init__()
+        self.bias = nn.Parameter(bias, requires_grad=False)
+
+    def forward(self, a):
+        def flipsign(x):
+            """Test functions defined within methods"""
+            return -x
+
+        for i in range(1000):
+            flipsign(a + self.bias)
+        return flipsign(a + self.bias)
+
+
+if __name__ == "__main__":
+    n_parallel = 3
+    devs = [torch.device(f"cuda:{i}") for i in range(n_parallel)]
+    modules = [
+        TestAdd(torch.randn(i + 1, 1, device=devs[i])) for i in range(n_parallel)
+    ]
+    args = [(torch.randn(i + 1, device=devs[i]),) for i in range(n_parallel)]
+    outputs = parallel_call(modules, args, do_profile=True)
+    print([f"{t.shape} : {t.device}" for t in outputs])
+    import glob, json
+
+    trace_files = glob.glob("./worker_*_trace.json")
+    print(trace_files)
+    merge_traces(trace_files, "merged_trace.json")
+
+    breakpoint()

torch_named_linops-0.3.10/dev/cuda_streams/merge_traces.py

@@ -0,0 +1,47 @@
+#!/usr/bin/env python
+#
+import glob
+import logging
+import json
+
+
+logger = logging.getLogger("torchmri")
+
+
+def main():
+    trace_files = glob.glob("./worker_*_trace.json")
+    logger.info(f"Found trace files ", trace_files)
+    merge_traces(trace_files, "merged_trace.json")
+
+
+def merge_traces(input_files, output_file):
+    """
+
+    Example usage
+    trace_files = glob.glob("./worker_*_trace.json")
+    merge_traces(trace_files, "merged_trace.json")
+    """
+    all_traces = {}
+    all_traces["traceEvents"] = []
+
+    for i, trace_file in enumerate(input_files):
+        with open(trace_file, "r") as f:
+            trace_data = json.load(f)
+            events = trace_data["traceEvents"]
+            for event in events:
+                event["pid"] = str(event["pid"]) + f"_{i}"
+
+            # Important step
+            all_traces["traceEvents"].extend(events)
+            # Less important steps
+            all_traces["schemaVersion"] = trace_data["schemaVersion"]
+            all_traces["deviceProperties"] = trace_data["deviceProperties"]
+    all_traces["traceName"] = str(output_file)
+
+    # Write combined traces to a new file
+    with open(output_file, "w") as f:
+        json.dump(all_traces, f)
+
+
+if __name__ == "__main__":
+    main()

torch_named_linops-0.3.10/dev/cuda_streams/profile_distributed_batch.py

@@ -0,0 +1,37 @@
+import torch
+
+from torchlinops import Dense, DistributedBatch
+from torch.profiler import profile, record_function, ProfilerActivity
+
+
+def main():
+    device_idxs = [0, 1]
+    devices = [torch.device(f"cuda:{idx}") for idx in device_idxs]
+    # device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+    B, M, N = 6, 100000, 10000
+    # Set up
+    weight = torch.randn(B, M, N, device="cpu")
+    A = Dense(weight, ("B", "M", "N"), ishape=("N",), oshape=("B", "M"))
+    A.to(devices[0])
+    A_batch = DistributedBatch(
+        A, devices[0], devices[0], torch.float32, torch.float32, devices=devices, B=1
+    )
+    # Prepare streams
+    # streams = [torch.cuda.Stream(devices[d % len(devices)]) for d in range(B)]
+    # default_streams = [torch.cuda.Stream(device) for device in devices]
+    # streams = [default_streams[d % len(devices)] for d in range(B)]
+    # for linop, stream in zip(A_batch._linops, streams):
+    #     linop.to(stream.device)
+
+    # y = torch.empty(B, M, device=devices[0])
+    x = torch.randn(N, device="cpu")
+    with profile(
+        activities=[ProfilerActivity.CPU, ProfilerActivity.CUDA],
+        on_trace_ready=lambda p: p.export_chrome_trace("./dist_trace.json"),
+    ) as prof:
+        for i in range(10):
+            y = A_batch(x)
+
+
+if __name__ == "__main__":
+    main()